As far as I know, if you're using a specific character model/Lora or just swapping face with insightface model... then it's actually difficult. If you want random characters to be put through sexual/nude ideas then that could be done.....
With all of its faults. It gets the lighting correct every damn time.... Flux is still improving - give it one more year and it'll be awesome.
Short serie (soft one)
Reproducing a famousYou must be registered to see the links
View attachment 4101970
You don't have permission to view the spoiler content. Log in or register now.
You don't have permission to view the spoiler content. Log in or register now.
You must be registered to see the links
I respectively disagree.
lmao speaking like someone who knows 0 about the subject.
LOL mate, quite the opposite.lmao speaking like someone who knows 0 about the subject.
You do realize there are different loras, checkpoints, styletransfers, embedding, hypernetoworks, loras, controlnets, VAEs, DoRAs, diffusion models, ipadapters, upscalers and first of all the possibility for endless prompting, right?
On top of that you have like 5 good base models in which you can work on and that have been exponentially getting better.
Dude sees an image probably done with a simple prompt on top of rundiffusion which isnt even a local stable diffusion where you have endless possibilities and is like "yeah AI Art is bad, despite these images being better than 99% of the renders in this thread and infinitely better than the monstruosity I have on my avatar that I call art".
Seriously?
lmao speaking like someone who knows 0 about the subject.
You do realize there are different loras, checkpoints, styletransfers, embedding, hypernetoworks, loras, controlnets, VAEs, DoRAs, diffusion models, ipadapters, upscalers and first of all the possibility for endless prompting, right?
On top of that you have like 5 good base models in which you can work on and that have been exponentially getting better.
Dude sees an image probably done with a simple prompt on top of rundiffusion which isnt even a local stable diffusion where you have endless possibilities and is like "yeah AI Art is bad, despite these images being better than 99% of the renders in this thread and infinitely better than the monstruosity I have on my avatar that I call art".
Seriously?
awam FAN ART thread. not artistic debate thread. please stop spamming.
are you using face swapper? what are your specs?
You answered to 0 of my arguments and instead posted 4 mid tier pieces of art.
Brilliant.
The edited image you posted looks, atleast to me, less photorealistic in parts due to you giving it a paintbrush kind of look making it appear more blurry aswell as robbing Sophia of her curves. It looks washed out. I'm not an artist so excuse my choice of words as I've no clue what exactly it's called, but it's as if you've been trying to turn an image aiming for photorealism into a painting.
TLDR; No, he's not alone with his statement. Clearly you just don't like AI art because it makes your work seem less special or whatever, and I can totally get behind that feeling, but it just is what it is. AI is the future in more ways than creating images better than any artist could ever do.
Sophia should get into a lactation kink and tell sam she needs help her breasts hurt..
beautiful work I was delighted
I only spent 5 minutes on it correcting mistakes and fixing lighting and shadows. Also added some blue tones to the shades as the scene lacked these and night shadows do have blue tones which that picture lacked. Nothing more. I would need to spend many hours to get the detail good enough to make it properly realistic. Majority of my professional work is not being brought to that level and also 100% realism does not look flashy so people don’t like it. Like I said most people will not even notice as the illusion is good enough. Also AI stuff posted is not photorealistic neither.
Guys, seriously, has anyone ever played this? Is it possible?
